Unveiling the role of plasticity rules in reservoir computing

Abstract

Reservoir Computing (RC) is an appealing approach in Machine Learning that combines the high computational capabilities of Recurrent Neural Networks with a fast and easy training method. Likewise, successful implementation of neuro-inspired plasticity rules into RC artificial networks has boosted the performance of the original models. In this manuscript, we analyze the role that plasticity rules play on the changes that lead to a better performance of RC. To this end, we implement synaptic and non-synaptic plasticity rules in a paradigmatic example of RC model: the Echo State Network. Testing on nonlinear time series prediction tasks, we show evidence that improved performance in all plastic models are linked to a decrease of the pair-wise correlations in the reservoir, as well as a significant increase of individual neurons ability to separate similar inputs in their activity space. Here we provide new insights on this observed improvement through the study of different stages on the plastic learning. From the perspective of the reservoir dynamics, optimal performance is found to occur close to the so-called edge of instability. Our results also show that it is possible to combine different forms of plasticity (namely synaptic and non-synaptic rules) to further improve the performance on prediction tasks, obtaining better results than those achieved with single-plasticity models.

References in corpus (2)

• Recent Advances in Physical Reservoir Computing: A Review
• Consistency in Echo-State Networks

Cited by in corpus (5)

• Reservoir computing based on solitary-like waves dynamics of film flows: a proof of concept
• Temporal Convolution Derived Multi-Layered Reservoir Computing
• Task learning through stimulation-induced plasticity in neural networks
• Prediction performance of random reservoirs with different topology for nonlinear dynamical systems with different number of degrees of freedom
• Plastic Arbor: a modern simulation framework for synaptic plasticity -- from single synapses to networks of morphological neurons